Large language model (LLM) services have recently begun offering a plugin ecosystem to interact with third-party API services. This innovation enhances the capabilities of LLMs, but it also introduces risks, as these plugins developed by various third parties cannot be easily trusted. This paper proposes a new attacking framework to examine security and safety vulnerabilities within LLM platforms that incorporate third-party services. Applying our framework specifically to widely used LLMs, we identify real-world malicious attacks across various domains on third-party APIs that can imperceptibly modify LLM outputs. The paper discusses the unique challenges posed by third-party API integration and offers strategic possibilities to improve the security and safety of LLM ecosystems moving forward. Our code is released at https://github.com/vk0812/Third-Party-Attacks-on-LLMs.
@article{arxiv.2404.16891,
title = {Attacks on Third-Party APIs of Large Language Models},
author = {Wanru Zhao and Vidit Khazanchi and Haodi Xing and Xuanli He and Qiongkai Xu and Nicholas Donald Lane},
journal= {arXiv preprint arXiv:2404.16891},
year = {2024}
}
Comments
ICLR 2024 Workshop on Secure and Trustworthy Large Language Models